Xiaoyu Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiaoyu Wang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Xiaojuan Ma
The Hong Kong University of Science and Technology, Hong Kong, China
3 shared publications - Shuai Ma
Institute of Software, Chinese Academy of Sciences, Beijing, China
2 shared publications - Tengxiang Zhang
GoerTek Inc., Beijing, China
2 shared publications - Xin Zeng
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2 shared publications - Yiqiang Chen
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2 shared publications - Yuanhao Zhang
CSE, Hong Kong University of Science and Technology, Hong Kong, China
2 shared publications
Latest Publications
- Open Access
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (6) , 1-38
Designing AI-Infused Interactive Systems for Online Communities: A Systematic Literature Review
AI-infused systems have demonstrated remarkable capabilities in addressing diverse human needs within online communities. Their widespread adoption has shaped user experiences and community dynamics at scale. However, designing such systems requires a clear understanding of user needs, careful design decisions, and robust evaluation. In this work, we present a systematic review of 77 studies on AI-infused systems in online communities, analyzing them through three lenses: the challenges they aim to address, their design functionalities, and the evaluation strategies employed. The first two dimensions are organized around four core aspects of community participation: contribution, consumption, mediation, and moderation. Our synthesis distills a set of key design lessons and considerations, including the necessity to design for broader community ecosystems and prioritize user emotional experiences. We conclude by outlining future directions, such as newcomer socialization and inclusive design.
- 23 September 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 10 (6) , 1-38
Open AccessDesigning AI-Infused Interactive Systems for Online Communities: A Systematic Literature Review
AI-infused systems have demonstrated remarkable capabilities in addressing diverse human needs within online communities. Their widespread adoption has shaped user experiences and community dynamics at scale. However, designing such systems requires a clear understanding of user needs, careful design decisions, and robust evaluation. In this work, we present a systematic review of 77 studies on AI-infused systems in online communities, analyzing them through three lenses: the challenges they aim to address, their design functionalities, and the evaluation strategies employed. The first two dimensions are organized around four core aspects of community participation: contribution, consumption, mediation, and moderation. Our synthesis distills a set of key design lessons and considerations, including the necessity to design for broader community ecosystems and prioritize user emotional experiences. We conclude by outlining future directions, such as newcomer socialization and inclusive design.
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussions
Asynchronous online discussions enable diverse participants to co-construct knowledge beyond individual contributions. This process ideally evolves through sequential phases, from superficial information exchange to deeper synthesis. However, many discussions stagnate in the early stages. Existing AI interventions typically target isolated phases, lacking mechanisms to progressively advance knowledge co-construction, and the impacts of different intervention styles in this context remain unclear and warrant investigation. To address these gaps, we conducted a design workshop to explore AI intervention strategies (task-oriented and/or relationship-oriented) throughout the knowledge co-construction process, and implemented them in an LLM-powered agent capable of facilitating progression while consolidating foundations at each phase. A within-subject study (N=60) involving five consecutive asynchronous discussions showed that the agent consistently promoted deeper knowledge progression, with different styles exerting distinct effects on both content and experience. These findings provide actionable guidance for designing adaptive AI agents that sustain more constructive online discussions.
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-27
Open Access"Shall We Dig Deeper?": Designing and Evaluating Strategies for LLM Agents to Advance Knowledge Co-Construction in Asynchronous Online Discussions
Asynchronous online discussions enable diverse participants to co-construct knowledge beyond individual contributions. This process ideally evolves through sequential phases, from superficial information exchange to deeper synthesis. However, many discussions stagnate in the early stages. Existing AI interventions typically target isolated phases, lacking mechanisms to progressively advance knowledge co-construction, and the impacts of different intervention styles in this context remain unclear and warrant investigation. To address these gaps, we conducted a design workshop to explore AI intervention strategies (task-oriented and/or relationship-oriented) throughout the knowledge co-construction process, and implemented them in an LLM-powered agent capable of facilitating progression while consolidating foundations at each phase. A within-subject study (N=60) involving five consecutive asynchronous discussions showed that the agent consistently promoted deeper knowledge progression, with different styles exerting distinct effects on both content and experience. These findings provide actionable guidance for designing adaptive AI agents that sustain more constructive online discussions.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-21
Signaling Human Intentions to Service Robots: Understanding the Use of Social Cues during In-Person Conversations
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-21
Open AccessSignaling Human Intentions to Service Robots: Understanding the Use of Social Cues during In-Person Conversations
- Open Access
- 24 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (ISS) , 462-499
GestureGPT: Toward Zero-Shot Free-Form Hand Gesture Understanding with Large Language Model Agents
Existing gesture interfaces only work with a fixed set of gestures defined either by interface designers or by users themselves, which introduces learning or demonstration efforts that diminish their naturalness. Humans, on the other hand, understand free-form gestures by synthesizing the gesture, context, experience, and common sense. In this way, the user does not need to learn, demonstrate, or associate gestures. We introduce GestureGPT, a free-form hand gesture understanding framework that mimics human gesture understanding procedures to enable a natural free-form gestural interface. Our framework leverages multiple Large Language Model agents to manage and synthesize gesture and context information, then infers the interaction intent by associating the gesture with an interface function. More specifically, our triple-agent framework includes a Gesture Description Agent that automatically segments and formulates natural language descriptions of hand poses and movements based on hand landmark coordinates. The description is deciphered by a Gesture Inference Agent through self-reasoning and querying about the interaction context (e.g., interaction history, gaze data), which is managed by a Context Management Agent. Following iterative exchanges, the Gesture Inference Agent discerns the user’s intent by grounding it to an interactive function. We validated our framework offline under two real-world scenarios: smart home control and online video streaming. The average zero-shot Top-1/Top-5 grounding accuracies are 44.79%/83.59% for smart home tasks and 37.50%/73.44% for video streaming tasks. We also provide an extensive discussion that includes rationale for model selection, generalizability, and future research directions for a practical system etc.
- 24 October 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Human-Computer Interaction
- Vol. 8 (ISS) , 462-499
Open AccessGestureGPT: Toward Zero-Shot Free-Form Hand Gesture Understanding with Large Language Model Agents
Existing gesture interfaces only work with a fixed set of gestures defined either by interface designers or by users themselves, which introduces learning or demonstration efforts that diminish their naturalness. Humans, on the other hand, understand free-form gestures by synthesizing the gesture, context, experience, and common sense. In this way, the user does not need to learn, demonstrate, or associate gestures. We introduce GestureGPT, a free-form hand gesture understanding framework that mimics human gesture understanding procedures to enable a natural free-form gestural interface. Our framework leverages multiple Large Language Model agents to manage and synthesize gesture and context information, then infers the interaction intent by associating the gesture with an interface function. More specifically, our triple-agent framework includes a Gesture Description Agent that automatically segments and formulates natural language descriptions of hand poses and movements based on hand landmark coordinates. The description is deciphered by a Gesture Inference Agent through self-reasoning and querying about the interaction context (e.g., interaction history, gaze data), which is managed by a Context Management Agent. Following iterative exchanges, the Gesture Inference Agent discerns the user’s intent by grounding it to an interactive function. We validated our framework offline under two real-world scenarios: smart home control and online video streaming. The average zero-shot Top-1/Top-5 grounding accuracies are 44.79%/83.59% for smart home tasks and 37.50%/73.44% for video streaming tasks. We also provide an extensive discussion that includes rationale for model selection, generalizability, and future research directions for a practical system etc.
- Open Access
- 13 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 344-351
Multi-channel Sensor Network Construction, Data Fusion and Challenges for Smart Home
- 13 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 344-351
Open AccessMulti-channel Sensor Network Construction, Data Fusion and Challenges for Smart Home
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
WebJump: AR-facilitated Distributed Display of Web Pages
Head-mounted displays (HMD) like AR glasses support powerful 3D displays and intuitive input modalities. However, there is a lack of collaboration between the HMD and other displays like PC monitors. In this paper, we propose WebJump, a software tool that analyzes HTML web pages and enables UI elements ‘jump’ from the PC monitor to the HMD. This way, contents like high-resolution images and long texts can take full advantage of the high-quality monitor display. Auxiliary contents like sidebars and menus, on the other hand, are offloaded to the HMD for easier access albeit with a lower display quality. We describe our software tool and explain in detail its implementation. We develop two applications to demonstrate WebJump’s feasibility and potential.
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessWebJump: AR-facilitated Distributed Display of Web Pages
Head-mounted displays (HMD) like AR glasses support powerful 3D displays and intuitive input modalities. However, there is a lack of collaboration between the HMD and other displays like PC monitors. In this paper, we propose WebJump, a software tool that analyzes HTML web pages and enables UI elements ‘jump’ from the PC monitor to the HMD. This way, contents like high-resolution images and long texts can take full advantage of the high-quality monitor display. Auxiliary contents like sidebars and menus, on the other hand, are offloaded to the HMD for easier access albeit with a lower display quality. We describe our software tool and explain in detail its implementation. We develop two applications to demonstrate WebJump’s feasibility and potential.